INDEX

Explanations

references to Australian culture and arts

oai_token-act-pair · gpt-4o-mini Triggered by @bot

Australian locations or culture

np_acts-logits-general · gemini-2.0-flash

australian places and culture

np_acts-logits-general · gemini-2.5-flash-lite

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.24.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

慳

-0.84

ReusableCell

-0.75

糅

-0.67

餸

-0.66

捱

-0.64



-0.64

ficheiro

-0.64

靚

-0.62

咭

-0.62

揀

-0.62

POSITIVE LOGITS

Pty

1.35

 Australian

1.33

 Australia

1.28

 Melbourne

1.28

 Queensland

1.28

 Brisbane

1.26

 Australians

1.26

Australian

1.25

NSW

1.25

 Canberra

1.22

Activations Density 0.512%

references to Australian culture and arts

Australian locations or culture

australian places and culture

No Comments

No Known Activations